Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 22142
    Prev
    Next
    INDEX
    Explanations

    words related to entitlement and government programs

    oai_token-act-pair · gpt-3.5-turbo

    references to entitlement and entitlement-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ucket
    -0.72
    olin
    -0.71
     Ou
    -0.71
     Archangel
    -0.69
     Fiber
    -0.68
    rawling
    -0.66
    hematic
    -0.65
    apest
    -0.65
     Coat
    -0.65
     Canon
    -0.64
    POSITIVE LOGITS
     entitle
    1.52
     entitlement
    1.09
     beneficiaries
    0.93
     entit
    0.87
     privileges
    0.82
     programmes
    0.80
     programs
    0.76
     afforded
    0.76
     obligations
    0.75
     lapse
    0.72
    Activations Density 0.005%

    No Known Activations